arXiv subjects

Xiaoxi Zhang

Publications and source records attributed to Xiaoxi Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Dude: A Dual-Detection Multi-Agent System for Paper-Code Discrepancy Detection

LLM-empowered paper-code discrepancy detection has received growing concern since the scaling of research submissions exceeds the manual review capability. However, the limited context capacity and one-sided discrepancy detection of existing single-agent LLM paradigms lead to an inferior recall performance in detecting discrepancies. In this paper, we propose Dude, the first Dual-Detection Multi-Agent System for paper-code discrepancy detection. We discover that the granularity asymmetry of the paper-language and code-language introduces over-interpretation and over-reporting challenges in a multi-agent system design for discrepancy detection, resulting in increasing false positives. To address this, we propose a granularity-aligned negotiation and a two-stage salience-filtering mechanism in Dude, which effectively prevents agents from falsely reporting discrepancies. Experimental results in real-world paper-code discrepancy datasets showcase Dude's significant recall and precision improvement by up to 22.8%, increasing F1 score by up to 18.7% compared to baseline methods.

cs.AI↗

arXiv2026

VeriNC: Finding Design Risks of In-Network Computing Systems

The emergence of programmable switches has brought in-network computing (INC) into the spotlight in recent years. By offloading computation directly onto the data transmission process, INC improves network utilization, reduces latency to sub-RTT levels, saves link bandwidth, and maintains throughput. However, INC disrupts the transparency of traditional networks, forcing developers to consider network exceptions like packet loss and out-of-order. If not properly handled, these exceptions can lead to violations of application properties, such as cache consistency and lock exclusion. Usual testing cannot exhaustively cover these exceptions, raising doubts about the correctness of INC systems and hindering their deployment in the industry. This paper presents VeriNC, the first general-purpose tool for verifying INC systems. VeriNC provides a high-level specification language and saves developers 67.2% lines of code on average. To help better understand the behavior of the system, VeriNC offers configurable network environments. VeriNC enables developers to express INC-specific correctness properties. VeriNC translates developer-specified systems into state transition representations, performs model checking to detect potential design risks, and reports violation traces to developers. We propose optimizations for INC-specific scenarios to address the challenge of state space explosion. We modeled INC systems across four application domains and identified design risks with VeriNC in seconds. VeriNC has also been adopted to guide the design of a new INC protocol. Based on our verification experience, we summarize lessons that help develop a correct INC protocol. We further reproduce them in real systems to confirm the validity of our verification result.

cs.DC↗

arXiv2026

Spatio-Temporal Parallelism for Diffusion Model Inference on Heterogeneous Multi-GPU Systems

The widespread adoption of diffusion models for image generation necessitates efficient parallel inference to manage their substantial computational overhead. However, current parallel inference paradigms primarily target homogeneous clusters, often failing to maintain high efficiency in realistic, heterogeneous multi-GPU environments where hardware disparities and fluctuating background workloads cause severe straggler effects. This paper introduces Orchestra, a robust framework that orchestrates fine-grained parallelism across both temporal and spatial dimensions to harmonize computational loads in such settings. Temporally, Orchestra employs a novel computation-aware step allocator using a tiered step reduction strategy, intelligently pruning denoising steps on slower devices after warmup phases and execution synchronization. Spatially, Orchestra performs an elastic patch parallelism mechanism which adaptively adjusts the spatial workload intensity by assigning non-uniform image patches tailored to GPUs according to their computational capability. Extensive experiments on load-imbalanced and heterogeneous clusters validate Orchestra's efficacy in mitigating performance bottlenecks. Compared to patch parallelism, a state-of-the-art diffusion inference framework, our method reduces end-to-end latency by up to 45% and significantly boosts resource utilization on heterogeneous GPUs.

cs.DC↗

arXiv2026

Decentralized Rank Scheduling for Energy-Constrained Multi-Task Federated Fine-Tuning in Edge-Assisted IoV Networks

Large-scale Internet of Vehicles (IoV) deployments increasingly demand the on-device adaptation of foundation models to support diverse, mission-critical perception tasks. While federated fine-tuning offers a promising solution for efficient model specialization, existing approaches often struggle to reconcile the inherent conflict between stringent global energy budgets, heterogeneous task demands, and the high volatility of vehicular network connectivity. In this work, we introduce a hierarchical, adaptive framework that decouples multi-task fine-tuning into two interdependent optimization phases. First, we implement a feedback-loop mechanism at the infrastructure level that dynamically redistributes global energy budgets across concurrent tasks based on real-time convergence dynamics and resource utilization. Second, at the vehicle level, we formulate intra-task rank selection as an energy-constrained online learning problem, solved via a novel primal-dual bandit algorithm, UCB-DUAL, which provides theoretical guarantees on sublinear regret. Our approach effectively internalizes global energy constraints into local decision-making, allowing vehicles to autonomously navigate the complex trade-off between model accuracy, latency, and power consumption. Empirical evaluations using a large-scale IoV simulator, driven by real-world trajectory data, confirm that our proposed method significantly outperforms current federated fine-tuning baselines, offering a robust and scalable solution for resource-constrained vehicular intelligence.

cs.LG↗

arXiv2026

Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement

The emergence of Mixture-of-Experts (MoE) has transformed the scaling of large language models by enabling vast model capacity through sparse activation. Yet, converting these performance gains into practical edge deployment remains difficult, as the massive memory footprint and communication demands often overwhelm resource-limited environments. While centralized cloud-based solutions are available, they are frequently plagued by prohibitive infrastructure costs, latency issues, and privacy concerns. Moreover, existing edge-oriented optimizations largely overlook the complexities of heterogeneous hardware, focusing instead on isolated or uniform device setups. In response, this paper proposes Prism, an inference framework engineered for collaborative MoE serving across diverse GPU-equipped edge servers. By leveraging the intrinsic sparsity and input locality of MoE workloads, Prism minimizes inter-server communication and optimizes expert placement within diverse resource constraints. The framework integrates an activation-aware placement strategy that balances local request coverage with memory utilization, supplemented by a runtime migration mechanism to adapt expert distribution to dynamic workload changes. Experiments on contemporary MoE models and datasets demonstrate that Prism reduces inference latency by up to 30.6% and significantly lowers communication costs compared to state-of-the-art baselines, confirming the effectiveness of cooperative edge-based MoE serving.

cs.DC↗

arXiv2026

Certifying the Right to Be Forgotten: Primal-Dual Optimization for Sample and Label Unlearning in Vertical Federated Learning

Federated unlearning has become an attractive approach to address privacy concerns in collaborative machine learning, for situations when sensitive data is remembered by AI models during the machine learning process. It enables the removal of specific data influences from trained models, aligning with the growing emphasis on the "right to be forgotten." While extensively studied in horizontal federated learning, unlearning in vertical federated learning (VFL) remains challenging due to the distributed feature architecture. VFL unlearning includes sample unlearning that removes specific data points' influence and label unlearning that removes entire classes. Since different parties hold complementary features of the same samples, unlearning tasks require cross-party coordination, creating computational overhead and complexities from feature interdependencies. To address such challenges, we propose FedORA (Federated Optimization for data Removal via primal-dual Algorithm), designed for sample and label unlearning in VFL. FedORA formulates the removal of certain samples or labels as a constrained optimization problem solved using a primal-dual framework. Our approach introduces a new unlearning loss function that promotes classification uncertainty rather than misclassification. An adaptive step size enhances stability, while an asymmetric batch design, considering the prior influence of the remaining data on the model, handles unlearning and retained data differently to efficiently reduce computational costs. We provide theoretical analysis proving that the model difference between FedORA and Train-from-scratch is bounded, establishing guarantees for unlearning effectiveness. Experiments on tabular and image datasets demonstrate that FedORA achieves unlearning effectiveness and utility preservation comparable to Retrain with reduced computation and communication overhead.

cs.CR↗

arXiv2025

SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference

The Mixture-of-Experts (MoE) architecture has been widely adopted in large language models (LLMs) to reduce computation cost through model sparsity. Employing speculative decoding (SD) can further accelerate MoE inference by drafting multiple tokens per step and verifying them in parallel. However, combining MoE with SD inflates GPU memory and aggravates CPU-GPU bandwidth contention during multi-token verification. Existing MoE offloading systems are SD-agnostic and do not address this bottleneck. We present SP-MoE, the first SD-aware expert-offloading and compute-communication pipelining framework. SP-MoE introduces: (1) speculative expert prefetching that exploits structural correspondence between the draft and target models to prefetch likely experts ahead of verification; (2) a cutoff-layer policy that bounds per-layer prefetch depth based on empirical profiles and an analytical latency model, guaranteeing just-in-time availability without overfetch; and (3) a pipelined runtime with asynchronous prefetch threads and batched I/O to hide loading latency. Extensive experiments demonstrate that SP-MoE achieves a 1.07-3.5 times TPOT speedup over state-of-the-art methods across diverse datasets, environments, and MoE-based models.

cs.DC↗

arXiv2025

Zero-energy band observation in an interfacial chalcogen-organic network

Structurally-defined molecule-based lattices such as covalent organic or metal-organic networks on substrates, have emerged as highly tunable, modular platforms for two-dimensional band structure engineering. The ability to grow molecule-based lattices on diverse platforms, such as metal dichalcogenides, would further enable band structure tuning and alignment to the Fermi level, which is crucial for the exploration and design of quantum matter. In this work, we study the emergence of a zero-energy band in a triarylamine-based network on semiconducting 1T-TiSe2 at low temperatures, by means of scanning probe microscopy and photoemission spectroscopy, together with density-functional theory. Hybridization between the position-selective nitrogens and selenium p-states results in CN-Se interfacial coordination motifs, leading to a hybrid molecule-semiconductor band at the Fermi level. Our findings introduce chalcogen-organic networks and showcase an approach for the engineering of organic-inorganic quantum matter.

physics.chem-ph↗

arXiv2025

TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction

Non-independent and identically distributed (Non-IID) data across edge clients have long posed significant challenges to federated learning (FL) training in edge computing environments. Prior works have proposed various methods to mitigate this statistical heterogeneity. While these works can achieve good theoretical performance, in this work we provide the first investigation into a hidden over-correction phenomenon brought by the uniform model correction coefficients across clients adopted by existing methods. Such over-correction could degrade model performance and even cause failures in model convergence. To address this, we propose TACO, a novel algorithm that addresses the non-IID nature of clients' data by implementing fine-grained, client-specific gradient correction and model aggregation, steering local models towards a more accurate global optimum. Moreover, we verify that leading FL algorithms generally have better model accuracy in terms of communication rounds rather than wall-clock time, resulting from their extra computation overhead imposed on clients. To enhance the training efficiency, TACO deploys a lightweight model correction and tailored aggregation approach that requires minimum computation overhead and no extra information beyond the synchronized model parameters. To validate TACO's effectiveness, we present the first FL convergence analysis that reveals the root cause of over-correction. Extensive experiments across various datasets confirm TACO's superior and stable performance in practice.

cs.LG↗

arXiv2025

Conditional-Marginal Nonparametric Estimation for Stage Waiting Times from Multi-Stage Models under Dependent Right Censoring

We investigate two population-level quantities (corresponding to complete data) related to uncensored stage waiting times in a progressive multi-stage model, conditional on a prior stage visit. We show how to estimate these quantities consistently using right-censored data. The first quantity is the stage waiting time distribution (survival function), representing the proportion of individuals who remain in stage j within time t after entering stage j. The second quantity is the cumulative incidence function, representing the proportion of individuals who transition from stage j to stage j' within time t after entering stage j. To estimate these quantities, we present two nonparametric approaches. The first uses an inverse probability of censoring weighting (IPCW) method, which reweights the counting processes and the number of individuals at risk (the at-risk set) to address dependent right censoring. The second method utilizes the notion of fractional observations (FRE) that modifies the at-risk set by incorporating probabilities of individuals (who might have been censored in a prior stage) eventually entering the stage of interest in the uncensored or full data experiment. Neither approach is limited to the assumption of independent censoring or Markovian multi-stage frameworks. Simulation studies demonstrate satisfactory performance for both sets of estimators, though the IPCW estimator generally outperforms the FRE estimator in the setups considered in our simulations. These estimations are further illustrated through applications to two real-world datasets: one from patients undergoing bone marrow transplants and the other from patients diagnosed with breast cancer.

stat.ME↗

arXiv2025

Online Location Planning for AI-Defined Vehicles: Optimizing Joint Tasks of Order Serving and Spatio-Temporal Heterogeneous Model Fine-Tuning

Advances in artificial intelligence (AI) including foundation models (FMs), are increasingly transforming human society, with smart city driving the evolution of urban living.Meanwhile, vehicle crowdsensing (VCS) has emerged as a key enabler, leveraging vehicles' mobility and sensor-equipped capabilities. In particular, ride-hailing vehicles can effectively facilitate flexible data collection and contribute towards urban intelligence, despite resource limitations. Therefore, this work explores a promising scenario, where edge-assisted vehicles perform joint tasks of order serving and the emerging foundation model fine-tuning using various urban data. However, integrating the VCS AI task with the conventional order serving task is challenging, due to their inconsistent spatio-temporal characteristics: (i) The distributions of ride orders and data point-of-interests (PoIs) may not coincide in geography, both following a priori unknown patterns; (ii) they have distinct forms of temporal effects, i.e., prolonged waiting makes orders become instantly invalid while data with increased staleness gradually reduces its utility for model fine-tuning.To overcome these obstacles, we propose an online framework based on multi-agent reinforcement learning (MARL) with careful augmentation. A new quality-of-service (QoS) metric is designed to characterize and balance the utility of the two joint tasks, under the effects of varying data volumes and staleness. We also integrate graph neural networks (GNNs) with MARL to enhance state representations, capturing graph-structured, time-varying dependencies among vehicles and across locations. Extensive experiments on our testbed simulator, utilizing various real-world foundation model fine-tuning tasks and the New York City Taxi ride order dataset, demonstrate the advantage of our proposed method.

cs.LG↗

arXiv2025

Real-Time Neural-Enhancement for Online Cloud Gaming

Online Cloud gaming demands real-time, high-quality video transmission across variable wide-area networks (WANs). Neural-enhanced video transmission algorithms employing super-resolution (SR) for video quality enhancement have effectively challenged WAN environments. However, these SR-based methods require intensive fine-tuning for the whole video, making it infeasible in diverse online cloud gaming. To address this, we introduce River, a cloud gaming delivery framework designed based on the observation that video segment features in cloud gaming are typically repetitive and redundant. This permits a significant opportunity to reuse fine-tuned SR models, reducing the fine-tuning latency of minutes to query latency of milliseconds. To enable the idea, we design a practical system that addresses several challenges, such as model organization, online model scheduler, and transfer strategy. River first builds a content-aware encoder that fine-tunes SR models for diverse video segments and stores them in a lookup table. When delivering cloud gaming video streams online, River checks the video features and retrieves the most relevant SR models to enhance the frame quality. Meanwhile, if no existing SR model performs well enough for some video segments, River will further fine-tune new models and update the lookup table. Finally, to avoid the overhead of streaming model weight to the clients, River designs a prefetching strategy that predicts the models with the highest possibility of being retrieved. Our evaluation based on real video game streaming demonstrates River can reduce redundant training overhead by 44% and improve the Peak-Signal-to-Noise-Ratio by 1.81dB compared to the SOTA solutions. Practical deployment shows River meets real-time requirements, achieving approximately 720p 20fps on mobile devices.

cs.NI↗

arXiv2025

Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligence

Recent years have witnessed a thriving growth of computing facilities connected at the network edge, cultivating edge networks as a fundamental infrastructure for supporting miscellaneous intelligent services.Meanwhile, Artificial Intelligence (AI) frontiers have extrapolated to the graph domain and promoted Graph Intelligence (GI). Given the inherent relation between graphs and networks, the interdiscipline of graph learning and edge networks, i.e., Edge GI or EGI, has revealed a novel interplay between them -- GI aids in optimizing edge networks, while edge networks facilitate GI model deployment. Driven by this delicate closed-loop, EGI is recognized as a promising solution to fully unleash the potential of edge computing power and is garnering growing attention. Nevertheless, research on EGI remains nascent, and there is a soaring demand within both the communications and AI communities for a dedicated venue to share recent advancements. To this end, this paper promotes the concept of EGI, explores its scope and core principles, and conducts a comprehensive survey concerning recent research efforts on this emerging field. Specifically, this paper introduces and discusses: 1) fundamentals of edge computing and graph learning,2) emerging techniques centering on the closed loop between graph intelligence and edge networks, and 3) open challenges and research opportunities of future EGI. By bridging the gap across communication, networking, and graph learning areas, we believe that this survey can garner increased attention, foster meaningful discussions, and inspire further research ideas in EGI.

cs.DC↗

arXiv2024

FedMoE-DA: Federated Mixture of Experts via Domain Aware Fine-grained Aggregation

Federated learning (FL) is a collaborative machine learning approach that enables multiple clients to train models without sharing their private data. With the rise of deep learning, large-scale models have garnered significant attention due to their exceptional performance. However, a key challenge in FL is the limitation imposed by clients with constrained computational and communication resources, which hampers the deployment of these large models. The Mixture of Experts (MoE) architecture addresses this challenge with its sparse activation property, which reduces computational workload and communication demands during inference and updates. Additionally, MoE facilitates better personalization by allowing each expert to specialize in different subsets of the data distribution. To alleviate the communication burdens between the server and clients, we propose FedMoE-DA, a new FL model training framework that leverages the MoE architecture and incorporates a novel domain-aware, fine-grained aggregation strategy to enhance the robustness, personalizability, and communication efficiency simultaneously. Specifically, the correlation between both intra-client expert models and inter-client data heterogeneity is exploited. Moreover, we utilize peer-to-peer (P2P) communication between clients for selective expert model synchronization, thus significantly reducing the server-client transmissions. Experiments demonstrate that our FedMoE-DA achieves excellent performance while reducing the communication pressure on the server.

cs.LG↗

arXiv2024

FedReMa: Improving Personalized Federated Learning via Leveraging the Most Relevant Clients

Federated Learning (FL) is a distributed machine learning paradigm that achieves a globally robust model through decentralized computation and periodic model synthesis, primarily focusing on the global model's accuracy over aggregated datasets of all participating clients. Personalized Federated Learning (PFL) instead tailors exclusive models for each client, aiming to enhance the accuracy of clients' individual models on specific local data distributions. Despite of their wide adoption, existing FL and PFL works have yet to comprehensively address the class-imbalance issue, one of the most critical challenges within the realm of data heterogeneity in PFL and FL research. In this paper, we propose FedReMa, an efficient PFL algorithm that can tackle class-imbalance by 1) utilizing an adaptive inter-client co-learning approach to identify and harness different clients' expertise on different data classes throughout various phases of the training process, and 2) employing distinct aggregation methods for clients' feature extractors and classifiers, with the choices informed by the different roles and implications of these model components. Specifically, driven by our experimental findings on inter-client similarity dynamics, we develop critical co-learning period (CCP), wherein we introduce a module named maximum difference segmentation (MDS) to assess and manage task relevance by analyzing the similarities between clients' logits of their classifiers. Outside the CCP, we employ an additional scheme for model aggregation that utilizes historical records of each client's most relevant peers to further enhance the personalization stability. We demonstrate the superiority of our FedReMa in extensive experiments.

cs.LG↗

arXiv2024

In-architecture X-ray assisted C-Br dissociation for on-surface fabrication of diamondoid chains

The fabrication of well-defined, low-dimensional diamondoid-based materials is a promising approach for tailoring diamond properties such as superconductivity. On-surface self-assembly of halogenated diamondoids under ultrahigh vacuum conditions represents an effective strategy in this direction, enabling reactivity exploration and on-surface synthesis approaches. Here we demonstrate through scanning probe microscopy, time-of-flight mass spectrometry and photoelectron spectroscopy, that self-assembled layers of dibromodiamantanes on gold can be debrominated at atomic wavelengths (Al K$α$ at 8.87 $\mathring{A}$ and Mg K$α$ at 9.89 $\mathring{A}$) and low temperatures without affecting their well-defined arrangement. The resulting 'in-architecture' debromination enables the fabrication of diamantane chains from self-assembled precursors in close proximity, which is otherwise inaccessible through annealing on metal surfaces. Our work introduces a novel approach for the fabrication of nanodiamond chains, with significant implications for in-architecture and layer-by-layer synthesis.

cond-mat.mtrl-sci↗

arXiv2024

Thermal spin-crossover and temperature-dependent zero-field splitting in magnetic nanographene chains

Nanographene-based magnetism at interfaces offers an avenue to designer quantum materials towards novel phases of matter and atomic-scale applications. Key to spintronics applications at the nanoscale is bistable spin-crossover which however remains to be demonstrated in nanographenes. Here we show that antiaromatic 1,4-disubstituted pyrazine-embedded nanographene derivatives, which promote magnetism through oxidation to a non-aromatic radical are prototypical models for the study of carbon-based thermal spin-crossover. Scanning tunneling spectroscopy studies reveal symmetric spin excitation signals which evolve at Tc to a zero-energy peak, and are assigned to the transition of a S = 3/2 high-spin to a S = 1/2 low-spin state by density functional theory. At temperatures below and close to the spin-crossover Tc, the high-spin S= 3/2 excitations evidence pronouncedly different temperature-dependent excitation energies corresponding to a zero-field splitting in the Hubbard-Kanamori Hamiltonian. The discovery of thermal spin crossover and temperature-dependent zero-field splitting in carbon nanomaterials promises to accelerate quantum information, spintronics and thermometry at the atomic scale.

physics.chem-ph↗

arXiv2023

DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset

Federated Learning (FL) is a distributed learning paradigm that can coordinate heterogeneous edge devices to perform model training without sharing private data. While prior works have focused on analyzing FL convergence with respect to hyperparameters like batch size and aggregation frequency, the joint effects of adjusting these parameters on model performance, training time, and resource consumption have been overlooked, especially when facing dynamic data streams and network characteristics. This paper introduces novel analytical models and optimization algorithms that leverage the interplay between batch size and aggregation frequency to navigate the trade-offs among convergence, cost, and completion time for dynamic FL training. We establish a new convergence bound for training error considering heterogeneous datasets across devices and derive closed-form solutions for co-optimized batch size and aggregation frequency that are consistent across all devices. Additionally, we design an efficient algorithm for assigning different batch configurations across devices, improving model accuracy and addressing the heterogeneity of both data and system characteristics. Further, we propose an adaptive control algorithm that dynamically estimates network states, efficiently samples appropriate data batches, and effectively adjusts batch sizes and aggregation frequency on the fly. Extensive experiments demonstrate the superiority of our offline optimal solutions and online adaptive algorithm.

cs.LG↗